Abstract Distributed systems have been widely used in many safety‐critical areas. Any abnormalities (e.g., service interruption or service quality degradation) could lead to application crashes or decrease user satisfaction. These things may cause serious economic losses. Among the various quality assurance approaches for distributed systems, log‐based anomaly detection (LAD) has become a popular research topic. Its popularity relates to system logs being able to record and reveal important run‐time information. This paper presents a general LAD framework for distributed systems. Log grouping and feature‐pattern mining are two crucial LAD components that impact on the anomaly‐detection effectiveness. We also present a systematic survey of techniques in these two directions; propose classification frameworks for log grouping and feature patterns; and summarize four log‐grouping techniques and five feature patterns (which refer to invariant relationships among logs that can be used for anomaly detection). To evaluate their applicability, we report on the findings when applying existing techniques to Ray, a popular industrial distributed system. Based on these findings, several open issues are identified, which provide potential guidance for future research and development.

Enhancing low-light images is challenging as it requires simultaneously handling global and local contents. This paper presents a new solution which incorporates the vision transformer (ViT) into Laplacian pyramid and explores cross-layer dependence within the pyramid. It first applies Laplacian pyramid to decompose the low-light image into a low-frequency (LF) component and several high-frequency (HF) components. As the LF component has a low resolution and mainly includes global attributes, ViT is applied on it to explore the interdependence among global contents. Since there exists strong spatial correlation among different frequency components, the refined features from a lower pyramid layer are used to assist the refinement of upper-layer features. Experiments demonstrate that our approach achieves better performance than state-of-the-art methods, while maintaining a relative small model size and low computational complexity. Our source code and trained model will be released at https://github.com/Xinjie-Wei/DLEN.

Since discriminant features are insufficient in the low-resolution (LR) images, it is challenging to accurately classify them. To address this issue, this paper proposes a joint super-resolution (SR) and classification network (JSRCN) based on bidirectional mapping and multiple constraints. In JSRCN, there is a SR sub-network containing a forward mapping path and several backward mapping paths. In the forward mapping path, high resolution (HR) features are progressively reconstructed. On the other hand, the backward mapping paths are used to alleviate the hardship of directly learning a nonlinear mapping from the LR space to the HR space. To effectively restore discriminant features for the image classification sub-network, multiple perceptual loss and multi-scale feature loss are presented to enhance the representation ability for the multi-scale features in images with different resolutions. Experiments show that compared with other competing methods, the proposed method achieves the highest accuracy.

Yield driven skew scheduling method leads to a clock tree with much greater wire length and buffer number that is not acceptable by designer. Geometry based register position relationships are converted to skew constraints and are combined with timing constraints harmoniously. With the two kinds of skew constraints together, our algorithm solves the skew scheduling problem for both restrictions and gives safety margins for not only timing variations but clocktree wire variations. It makes the yield driven clock network realizable inpractical design. Experimental results show that our algorithm has 72.7% yield improvement then normal scheduling. In addition, the clock tree wire length and buffer number are reduced by 52.2% and 40.4% compared with previous yielddriven skew scheduling method.

Iterative slack distribution is a prevalent method in timing analysis and clock scheduling. Finding minimum mean cycle is the most time consuming step in the each iterative process. We present a practical strategy that can speed up the loop. A fast negative cycle detection method is used for examining whether the cycle of length two is really the minimum mean cycle. Traditional complicated minimum mean cycle algorithm can be skipped during the iterative slack distribution process. Experimental results show that our method can reduce running time of the iterative slack distribution process. The percentages are from 47% to 90% for different benchmark circuits.